Daddy Dave's stamp of approval 👍
4-bit GPTQ quants of the writer version of Sao10K's fantastic Stheno model (Stheno model collection link)
The main branch contains 4-bit groupsize of 128 and no act_order.
The other branches contain groupsizes of 128, 64, and 32 all with act_order.
⬇︎ Original card ⬇︎
My GGUF Quants: https://huggingface.co/Sao10K/Stheno-1.10-L2-13B-GGUF
Oh, you thought there'd be a 2.0? Nope. Not yet.
A recreation of Stheno with Updated versions of the same models and Merging Values. Feels more coherent, and is uncensored (zero context) at least according to my tests.
Is somewhat smarter, I think? Atleast it passes 4/5 times in my own test suites.
Feel free to try it out, I'd appreciate Feedback.
Most formats could work, but my tests have all been done in Alpaca format and it works well.
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
support me here :)
Once Again, thanks to Chargoddard for his amazing and simple mergekit script. Thanks to the original model creators too!
- Downloads last month
- 16